AI agents call get_commission to retrieve information from Hotmart without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves commission summary information from the Hotmart platform. It queries existing data without creating, modifying, deleting, or executing any operations. No financial transactions are initiated. The read-only nature and simple retrieval operation classify it as a Read risk, with low severity since it only accesses summary data without ability to change platform state or commit financial obligations.
From the tool's definition The tool name is 'get_commission' and description is 'Get commission summary' — both indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get commission summary. It is categorised as a Read tool in the Hotmart MCP Server, which means it retrieves data without modifying state.
Register the Hotmart MCP server in PolicyLayer and add a rule for get_commission: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Hotmart. Nothing to install.
get_commission is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_commission rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_commission. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_commission is provided by the Hotmart MCP server (theyahia/hotmart-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →